works on
hierarchical global attention 1kv cache offloading 1long-context training 1memory management 1parameter-efficient fine-tuning 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.AI2026

Long-Context Fine-Tuning with Limited VRAM

Vladimir Fedosov, Aleksandr Sazhin, Artemiy Grinenko +1

The paper introduces Hierarchical Global Attention combined with segment-wise backpropagation and tiered key‑value storage to fine‑tune large language models on much longer sequenc…